version 5.2.3

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

README.md

@@ -507,6 +507,9 @@ hbc --boot your-server.example.com
 
 # Verbose output
 hbc -v your-server.example.com
+
+# Send 'boot' and 'shutdown' messages on start and exit 
+hbc -b your-server.example.com
 ```
 
 You can also run it via the module entrypoint:

hbd/__init__.py

@@ -14,4 +14,4 @@ Install options:
 """
 
 __all__ = ["__version__"]
-__version__ = "5.2.1"
+__version__ = "5.2.3"

hbd/client/main.py

@@ -21,6 +21,7 @@ from typing import Dict, List, Optional
 # Import protocol and config
 from .config import load_config
 from ..common.proto import dicttos, stodict
+from .. import __version__
 
 # Import plugin system
 from .plugin import PluginRegistry, PluginLoader, InfoPlugin, MonitorPlugin
@@ -172,9 +173,8 @@ class HeartbeatProtocol(asyncio.DatagramProtocol):
             self.logger.error(f"Error processing datagram: {e}", exc_info=True)
     
     def error_received(self, exc):
-        """Handle protocol errors."""
+        """Handle protocol errors — close transport so the heartbeat sender retries."""
-        self.logger.warning(f"Protocol error on {self.connection.addr}: {exc} — dropping connection")
+        self.logger.warning(f"Protocol error on {self.connection.addr}: {exc} — will retry")
-        self.connection._dead = True
         self.connection.close()
 
 
@@ -464,7 +464,7 @@ async def cleanup(connections: List[AsyncConnection]):
     logger.info("Cleaning up connections")
     
     target = next((c for c in connections if c.transport), connections[0] if connections else None)
-    if target:
+    if target and send_shutdown:
         try:
             await target.sendto({"shutdown": 1, "acks": target.ackcount})
         except Exception as e:
@@ -478,7 +478,7 @@ async def cleanup(connections: List[AsyncConnection]):
 
 async def async_main(args, config):
     """Async main function."""
-    global running, shutdown_event, active_tasks
+    global running, shutdown_event, active_tasks, send_shutdown 
     
     # Create shutdown event
     shutdown_event = asyncio.Event()
@@ -495,6 +495,7 @@ async def async_main(args, config):
     hb_port = config.get("hb_port", PORT)
     interval = config.get("interval", INTERVAL)
     
+    logger.info(f"hbc {__version__} starting on {iam}")
     logger.info(f"Starting hbc for {iam} -> {hb_hosts}")
     logger.info(f"Port: {hb_port}, Interval: {interval}s")
     
@@ -526,10 +527,13 @@ async def async_main(args, config):
     logger.info(f"Created {len(connections)} connections")
     
     # Send boot/message if requested
+    send_shutdown = False
     if args.boot or args.message:
         boot_msg = {}
         if args.boot:
             boot_msg["boot"] = 1
+            args.boot = False  # Clear boot flag so we don't send it again in main loop
+            send_shutdown = True
         if args.message:
             boot_msg["service"] = "service"
             boot_msg["msg"] = args.message

hbd/client/plugins/ping_monitor.py

@@ -13,12 +13,8 @@ plugins:
     count: 3              # ICMP packets per ping run (default 3)
     timeout: 5            # seconds before a host is considered unreachable (default 5)
     hosts:
-      8.8.8.8:
+      - 8.8.8.8
-        warning: 20.0     # ms
+      - 192.168.1.1
-        critical: 100.0   # ms
-      192.168.1.1:
-        warning: 5.0
-        critical: 20.0
 ```
 
 Reported metrics per host (metric key uses the hostname with dots/colons replaced

hbd/server/main.py

@@ -475,7 +475,8 @@ def run(config, config_path=None):
     if config.get("debug", 0) > 0:
         log_level = logging.DEBUG
     logging.basicConfig(level=log_level)
-    logging.getLogger("aiohttp.access").setLevel(logging.DEBUG)
+    if not config.get("debug", 0):
+        logging.getLogger("aiohttp.access").propagate = False
     load_pickled_hosts(config, hbdclass)
 
     notify_mod.initlog(logfile=config.get("logfile", "messages.log"))

hbd/server/templates/alerts.html

@@ -184,9 +184,9 @@
     }
 
     .alert-metric {
-      color: #666;
+      color: #0066cc;
-      font-family: 'Courier New', monospace;
+      font-size: 1.1em;
-      font-size: 0.9em;
+      font-weight: normal;
     }
 
     .alert-details {
@@ -438,8 +438,8 @@
               <div class="alert-header">
                 <span class="alert-level ${level}">${alert.level}</span>
                 <a class="alert-hostname" href="/plugins#${alert.hostname}">${alert.hostname}</a>
+                <span class="alert-metric">${alert.metric_path.includes('.') ? alert.metric_path.slice(alert.metric_path.indexOf('.') + 1) : alert.metric_path}</span>
               </div>
-              <div class="alert-metric">${alert.metric_path}</div>
               <div class="alert-details">
                 <span>${valueText}</span>
                 <span class="alert-duration">Active for ${duration}</span>

hbd/server/threshold.py

@@ -1109,11 +1109,16 @@ class ThresholdChecker:
         if host is not None and not host.watched:
             eventlog(host_name, lvl, message, service="threshold")
             return
+        short_path = metric_path.partition(".")[2] or metric_path
+        title = f"[{lvl}] {host_name}  {short_path}"
+        # Strip the "metric = " prefix from message so body is just the value/detail
+        prefix = short_path + " = "
+        body = message[len(prefix):] if message.startswith(prefix) else message
         asyncio.get_event_loop().create_task(notify_mod.send_notification(
             host_name,
             notify_mod.Notification(
-                title=f"[{lvl}] {host_name}",
+                title=title,
-                body=message,
+                body=body,
                 level=lvl,
             ),
         ))
@@ -1358,18 +1363,19 @@ class ThresholdChecker:
                     check_name=check_name,
                     metric_name=metric_name,
                 )
-                message = f"REMINDER ({alert_state.level.name}): {host_name} - {short_path} = {value} {threshold_info}, ongoing for {int(now - alert_state.since)}s"
+                body = f"{value} {threshold_info}, ongoing for {int(now - alert_state.since)}s"
             else:
-                message = f"REMINDER ({alert_state.level.name}): {host_name} - {short_path} = {value} (ongoing for {int(now - alert_state.since)}s)"
+                body = f"{value} (ongoing for {int(now - alert_state.since)}s)"
-            
+            message = f"REMINDER ({alert_state.level.name}): {host_name} - {short_path} = {body}"
+
             from . import hbdclass
             host = hbdclass.Host.hosts.get(host_name)
             if host is None or host.watched:
                 asyncio.get_event_loop().create_task(notify_mod.send_notification(
                     host_name,
                     notify_mod.Notification(
-                        title=f"[REMINDER/{alert_state.level.name}] {host_name}",
+                        title=f"[REMINDER/{alert_state.level.name}] {host_name}  {short_path}",
-                        body=message,
+                        body=body,
                         level=alert_state.level.name,
                     ),
                 ))

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hbd"
-version = "5.2.1"
+version = "5.2.3"
 description = "Heartbeat monitoring system — client (hbc) and server (hbd)"
 readme = "README.md"
 requires-python = ">=3.11"

scripts/hbc_mini.py

@@ -41,7 +41,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple
 
 # updated by scripts/bumpminor.sh
-__version__ = "5.2.1"
+__version__ = "5.2.3"
 
 # ---------------------------------------------------------------------------
 # Protocol  (mirrors hbd/common/proto.py)
@@ -797,8 +797,7 @@ class _HeartbeatProtocol(asyncio.DatagramProtocol):
             self._log.error("datagram error: %s", e)
 
     def error_received(self, exc):
-        self._log.warning("protocol error on %s: %s — dropping connection", self._conn.addr, exc)
+        self._log.warning("protocol error on %s: %s — will retry", self._conn.addr, exc)
-        self._conn._dead = True
         self._conn.close()
 
 
@@ -1029,7 +1028,7 @@ def _reconfigure_syslog(level: int):
 # ---------------------------------------------------------------------------
 
 async def _async_main(args, cfg: Dict[str, Any]) -> int:
-    global _running, _shutdown_event, _active_tasks
+    global _running, _shutdown_event, _active_tasks, send_shutdown
     _running = True
     _shutdown_event = asyncio.Event()
     _active_tasks = []
@@ -1039,7 +1038,7 @@ async def _async_main(args, cfg: Dict[str, Any]) -> int:
     port = cfg.get("hb_port", PORT)
     interval = cfg.get("interval", INTERVAL)
 
-    log.info("starting: %s -> %s port=%d interval=%ds", iam, args.hosts, port, interval)
+    log.info("starting hbc_mini %s on %s -> %s port=%d interval=%ds",__version__, iam, args.hosts, port, interval)
 
     connections: List[AsyncConnection] = []
     conn_id = 1
@@ -1060,10 +1059,13 @@ async def _async_main(args, cfg: Dict[str, Any]) -> int:
         return 1
 
     # Boot / one-shot message
+    send_shutdown = False
     if args.boot or args.message:
         bmsg: Dict[str, Any] = {"acks": 0}
         if args.boot:
             bmsg["boot"] = 1
+            args.boot = False  # don't repeat on restart
+            send_shutdown = True
         if args.message:
             bmsg["service"] = "service"
             bmsg["msg"] = args.message
@@ -1101,7 +1103,7 @@ async def _async_main(args, cfg: Dict[str, Any]) -> int:
 
     log.info("shutting down")
     target = next((c for c in connections if c._transport), connections[0] if connections else None)
-    if target:
+    if target and send_shutdown:
         try:
             await target.sendto({"shutdown": 1, "acks": target.ackcount})
         except Exception: